Copyright © 2015, SAS Institute Inc. All right reserved.
By: Anders Richter, SAS Institute, Denmark
Forecast Value-Added
Copyright © 2015, SAS Institute Inc. All right reserved.
Agenda
Introduction
Demand-Driven Planning & Optimization (DDPO)
Common challenges and demands
Demand synchronization
The Process
Forecasting
Collaborative Planning
Forecast Value-Added(Next presentation has focus on Inventory Optimization)
Copyright © 2015, SAS Institute Inc. All right reserved.
WHO IS ANDERS RICHTER
Education from Copenhagen Business School:
• Master of Science in Business Administration, math, statistics and
economy
• Graduate diploma in supply chain management
7 years’ experience as analytical consultant with several forecasting and
inventory optimization implementations
I have had several classical roles, i.e. business advisor in the sales process,
system designer, ETL coding, analytic business expert and project
manager
Contributed with input to the book
“Demand-Driven Inventory
Optimization and Replenishment”,
Chapter 8 Matas, a case study,
Chapter 9 A consultant’s view of
inventory optimization
Copyright © 2015, SAS Institute Inc. All right reserved.
Demand-Driven
Planning &
Optimization
REFERENCES
ESCAPO
CV Vooruit
Copyright © 2015, SAS Institute Inc. All right reserved.
Demand-Driven
Planning &
Optimization
COMMON CHALLENGES AND DEMANDS
Incoherent flows
High stock values
Many out-of-stock (OOS) situations
Many manual processes
Gut feeling instead of facts
Many man-hours spent on
replenishment
Coherent replenishment flow
Forecasting based on POS data
Automated orders
Fewer man-hours
Higher turnover rate
Fewer OOS situations
Especially on critical articles
Copyright © 2015, SAS Institute Inc. All right reserved.
Demand-Driven
Planning &
Optimization
DEMAND SYNCHRONIZATION
Sense demand signals faster to changes in the marketplace.
Align supply chain faster to fluctuations in demand.
Align demand and supply with improved customer service with
substantially less inventory, waste and working capital
Three primary goals
Copyright © 2015, SAS Institute Inc. All right reserved.
Lean Lean
Forecasting Management
(FVA)
Demand-Driven
Planning &
Optimization
DEMAND SYNCHRONIZATION
Market Supplier
Demand-
Driven
Sales & Operations Planning
Market-
Driven
Selling through the channel (pull) Selling into the channel (push)
Supply-
Driven
Supply Sensing
Supply Shaping
Synchronized
Replenishment
Inside-out
Focused
Reactive
Process
Inventory
Optimization
Demand Sensing
Demand Shaping
Demand Shifting
Outside-in
Focused
Proactive
Process
Collaborative
Planning
Copyright © 2015, SAS Institute Inc. All right reserved.
Demand-Driven
Planning &
Optimization
THE PROCESS
Copyright © 2015, SAS Institute Inc. All right reserved.
Forecasting THE LAWS OF FORECASTING
1. Forecasts are almost always wrong!
2. Forecasts for near future are more accurate
3. Forecasts on SKU level are usually less
accurate than forecasts on product group level
4. Forecasts cannot substitute calculated values
Copyright © 2015, SAS Institute Inc. All right reserved.
Forecasting RESULTS OF POOR FORECASTING
Forecast Error
Over Forecast Under Forecast
Excess Inventory
Holding Cost
Transshipment Cost
Obsolescence
Reduce Margin
Expediting Cost
Higher Product Cost
Lost Sales Cost
Lost Companion Sales
Customer Satisfaction
Copyright © 2015, SAS Institute Inc. All right reserved.
Forecasting LARGE-SCALE FORECASTING
Time Series Data
80% can be forecasted automatically
10% require extra effort
10% cannot be forecasted accurately
Copyright © 2015, SAS Institute Inc. All right reserved.
Forecasting HIERARCHICAL FORECAST
Hierarchies:
• Product dimension
• Customer dimension
• Network dimension
Company
Warehouse
Store
Copyright © 2015, SAS Institute Inc. All right reserved.
ForecastingEXAMPLE FROM A HIGH-PERFORMANCE
FORECASTING (HPF) INSTALLATION
• 2 levels in the forecast hierarchy
• 2 million forecasts each week for SKU/store combinations
(52 weeks on a weekly level, based on up to 3 years of data)
• 30,000 forecasts each day on SKU level
(52 weeks on a daily level, based on up to 3 years of data)
• Forecast is reconciled each day
• Model types: ARIMAX, ESM and pre-made naïve models
• Causal factors
Flyer, avis, smuk, jule, uann, x_kampagne, vareOvergang,
forside, familie_rabat, soendags_aabent, kamp_uge_1,
kamp_uge_2 and uannon_periode
• Output is expected sales on SKU/store and SKU level,
and the uncertainty of the excepted sales
Copyright © 2015, SAS Institute Inc. All right reserved.
Demand-Driven
Planning &
Optimization
THE PROCESS
Copyright © 2015, SAS Institute Inc. All right reserved.
Collaborative
PlanningCOLLABORATIVE WORKFLOW
Statistical
ModelDemand
History
Causal
Factors
Consensus
Forecast
Sales
Mktg
Product
MgmtP&IC
Finance
Exec
Targets
Executive
Approval
Analyst
Override
Gather data on the forecasts of
all process steps and
participants
• Statistical forecast
• Analyst override
• Collaborative /
consensus process input
• Executive Approval
• (Naïve Forecast)
Copyright © 2015, SAS Institute Inc. All right reserved.
Collaborative
Planning
FORECAST VALUE-ADDED (FVA)
Focus on forecasting process efficiency
Forecast accuracy is largely a function of the “forecastability” of the demand
We may never be able to achieve the accuracy desired
But we can control the process used and the resources we invest
Our objective:
Generate forecasts as accurate and unbiased as we
can reasonably expect them to be, and to do this as
efficiently as possible
Copyright © 2015, SAS Institute Inc. All right reserved.
Collaborative
Planning
FORECAST VALUE-ADDED (FVA)
Performance must always be evaluated with respect to the alternatives
The “naïve” forecast
The naïve forecast is a baseline of performance against which all forecasting efforts must
be compared
Two commonly used naïve models are:
Random Walk
Seasonally Adjusted Random Walk
If you cannot beat a naïve forecast, then why bother?
Copyright © 2015, SAS Institute Inc. All right reserved.
Collaborative
Planning
FORECAST VALUE-ADDED (FVA)
An example of a FVA Report
Copyright © 2015, SAS Institute Inc. All right reserved.
Collaborative
Planning
FORECAST VALUE-ADDED (FVA)
Forecasting performance evaluation
Who is the best analyst and should have a bonus?
Analyst Item TypeItem Life
CycleSeasonal Promos
New Items
Demand Volatility
MAPE
A Basic Long No None None Low 20%
B Basic Long Some Few Few Medium 30%
C Fashion Short Highly Many Many High 40%
Naïve MAPE FVA
10% -10%
30% 0%
50% 10%
Copyright © 2015, SAS Institute Inc. All right reserved.
Collaborative
Planning
FORECAST VALUE-ADDED (FVA)
• FVA analysis compares the results of each process activity to the results
that would have been achieved without doing the activity
• A naïve forecast provides a relevant baseline for comparing to the
process activities
• Must also evaluate the performance of sequential
steps in the process
Copyright © 2015, SAS Institute Inc. All right reserved.
Collaborative
Planning
FORECAST VALUE-ADDED (FVA) EXAMPLE
Copyright © 2015, SAS Institute Inc. All right reserved.
Copyright © 2015, SAS Institute Inc. All right reserved.
Anders Richter
Business Delivery Manager
Commercial & Life Sciences Division
SAS Institute Denmark
E-mail: [email protected]
Mobile: +45 27 21 28 21
Or follow me on LinkedIn